verifier.org

KoboldCpp

one portable binary, no install, and an agpl licence that obliges you to share modifications you host.

free#creative-writing#roleplay#anyone-who-wants-zero-in

genuinely open with the strictest obligations here — the copyleft cuts against companies rather than users, which is the opposite of everyone else's catch.

it ships as a single dependency-free executable bundling a server and the kobold lite web ui. no installer, no runtime, no package manager — download and run. for a category where setup friction is the main barrier, that is a real design achievement.

the feature set leans towards long-form fiction and roleplay: memory, world info, instruct and chat modes, all built around keeping a long narrative coherent rather than answering one-off questions. cuda, rocm, vulkan and cpu via its own llama.cpp fork.

the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.

pricing
free
website
github.com
our verdict

genuinely open with the strictest obligations here — the copyleft cuts against companies rather than users, which is the opposite of everyone else's catch.

we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.

more local llm tools

Text Generation WebUI

oobabooga's gradio interface for running local models and loaders

#open-source#gradio

vLLM

high-throughput serving engine you can run on your own gpu

#serving#throughput

MLX LM

apple's framework for running and fine-tuning models on apple silicon

#apple-silicon

Jan

we checked thisfree

gui, server and inference engine all apache 2.0 — the only tool here where every layer is genuinely open.

#anyone-who-wants-ollama-